Architecture and integrations
Understand and design agents, RAG, memory, orchestration, APIs, MCP, and tool integrations, including their control and security boundaries.
Start here
Begin with these resources. The sections below organize the rest of the topic by subject.
-
Article
LLM vs. AI System Capabilities: What Architecture Adds
See what memory, retrieval, tools, and verification add to a base model and which limitations remain.Read article -
Reference
AI API and Agent Architecture: Where Instructions, State, and Tools Belong
Locate instructions, retrieval, tools, and runtime inputs in an API or internal agent system.Open reference -
Guide
Software Architecture Boundary Review: Step-by-Step Guide
Review ownership, interfaces, and dependency boundaries in an existing design.Open guide
Components and capabilities
How LLMs, retrieval, agents, and MCP divide the work, and where a system still falls short of the user's goal.
-
Article
LLMs, RAG, AI Agents, and MCP: How They Work Together
A technical comparison of LLMs, RAG, AI agents, and MCP across four architectural responsibilities: generation, retrieval, action selection, and protocol integration.Read article -
Article
How AI Performs Human-Like Tasks—and Where the Gaps Remain
A 22-row architecture map that turns common LLM capability gaps into external controls, implementation patterns, and residual validation questions.Read article -
Article
When AI Systems Optimize Against the User’s Real Goal
How competing system objectives can produce acceptable outputs without completing the user’s actual task.Read article -
Article
Parallel LLM Reasoning: Sampling, Search, and Synthesis
Why multi-path reasoning around standard autoregressive LLMs usually depends on inference-time branching, evaluation, and synthesis—and where newer architectures differ.Read article
Memory, context, and retrieval
What an agent stores, what reaches the model on each call, and how to control which sources influence an answer.
-
Article
What Does It Take for an AI Agent to Remember?
A vendor-agnostic systems model for LLM agent memory types, working state, persistent memory, representation and storage choices, lifecycle controls, and evaluation.Read article -
Article
LLM Memory vs. Context: 5 Architecture Boundaries
A vendor-agnostic model of five boundaries that separate stored state from model-visible context: invocation, persistence, retrieval, context assembly, and updates.Read article -
Article
User Prompt vs. Model Context: What an LLM Actually Receives
A user prompt is one part of model context. Learn which instructions, history, files, retrieved data, tools, and memory can become model-visible—and which may remain outside the current inference.Read article -
Guide
How to Control AI Memory and Context Sources
Identify whether prompts, files, past chats, saved memory, project context, retrieval, apps, or backend state influenced an AI answer—and remove unwanted context.Open guide
Tools and orchestration
Who decides the next tool call, how controller loops and agent handoffs work, and what connected apps are allowed to do.
-
Article
Tool-Using LLMs: Model-Led vs. Orchestrator-Led Execution
A control-plane placement comparison for tool-using LLM systems, covering reliability, observability, latency, cost governance, and security.Read article -
Article
AI Agent Orchestration Loops: Security Risks and Controls
How multi-step orchestration (controller) loops change the threat model in tool-using systems, and where to enforce separation, authorization, validation, and budgets to reduce prompt injection, tool misuse, unsafe writes, and unbounded consumption.Read article -
Article
How a Forged Message Can Hijack an AI Workflow
A forged message can turn a release review into an unauthorized deployment. Follow the handoff between AI agents to see why message verification and action authorization require separate checks.Read article -
Article
Connected Apps and MCP Security: Permissions, Data, and Actions
Security analysis of connected apps, external tools, and remote MCP servers as capability, scope, approval, disclosure, and side-effect control surfaces.Read article
Security boundaries in integrations
Threat-model the integration layer, request assembly, permissions, and web retrieval, and protect private data in agent workflows.
-
Article
LLM Integration Trust Boundaries: Threat Modeling Before AI Agents
Why LLM security begins at the integration layer: it turns model inputs and outputs into access to data, system actions, and persistent artifacts before an agent loop exists.Read article -
Article
Request Assembly Threat Model for AI Agents
A reviewer-oriented threat model for request assembly in AI assistants: what enters context, what gets prioritized or dropped, and where policy, tool, memory, retrieval, and audit checkpoints should be reviewed.Read article -
Article
LLM Prompt Assembly Security: Policy and Untrusted Data
An engineering guide to preventing authority confusion in prompt assembly by separating authoritative policy from untrusted content with typed provenance.Read article -
Article
AI Tool Security: Persistent Permissions and Unenforced Alerts
Two vendor-agnostic control-plane failure patterns—privilege persistence across interaction boundaries and non-enforcing integrity signals—that allow untrusted state to steer tool execution across steps.Read article -
Article
Prompt Injection in AI Web Retrieval: Risks and Controls
A threat model for browsing-enabled and tool-using LLM systems where retrieved web content can steer routing, tool arguments, follow-up calls, or side effects.Read article -
Guide
Protect Gmail and WhatsApp Data in AI Agent Workflows
Protect Gmail and WhatsApp data when AI agents access private messages, attachments, tools, connected apps, and backend workflows.Open guide
Review a design or implementation
Check an implementation against official documentation and standards, with Skills and policies for architecture and implementation reviews.